tracing/probes: Support function parameters if BTF is available

Support function or tracepoint parameters by name if BTF support is enabled
and the event is for function entry (this feature can be used with kprobe-
events, fprobe-events and tracepoint probe events.)

Note that the BTF variable syntax does not require a prefix. If it starts
with an alphabetic character or an underscore ('_') without a prefix like
'$' and '%', it is considered as a BTF variable.
If you specify only the BTF variable name, the argument name will also
be the same name instead of 'arg*'.

 # echo 'p vfs_read count pos' >> dynamic_events
 # echo 'f vfs_write count pos' >> dynamic_events
 # echo 't sched_overutilized_tp rd overutilized' >> dynamic_events
 # cat dynamic_events
p:kprobes/p_vfs_read_0 vfs_read count=count pos=pos
f:fprobes/vfs_write__entry vfs_write count=count pos=pos
t:tracepoints/sched_overutilized_tp sched_overutilized_tp rd=rd overutilized=overutilized

Link: https://lore.kernel.org/all/168507474014.913472.16963996883278039183.stgit@mhiramat.roam.corp.google.com/

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Tested-by: Alan Maguire <alan.maguire@oracle.com>

Author: mhiramat

kernel/trace/Kconfig

@@ -664,6 +664,18 @@ config FPROBE_EVENTS
 	  and the kprobe events on function entry and exit will be
 	  transparently converted to this fprobe events.
 
+config PROBE_EVENTS_BTF_ARGS
+	depends on HAVE_FUNCTION_ARG_ACCESS_API
+	depends on FPROBE_EVENTS || KPROBE_EVENTS
+	depends on DEBUG_INFO_BTF && BPF_SYSCALL
+	bool "Support BTF function arguments for probe events"
+	default y
+	help
+	  The user can specify the arguments of the probe event using the names
+	  of the arguments of the probed function, when the probe location is a
+	  kernel function entry or a tracepoint.
+	  This is available only if BTF (BPF Type Format) support is enabled.
+
 config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API

kernel/trace/trace.c

@@ -5698,7 +5698,11 @@ static const char readme_msg[] =
 	"\t     args: <name>=fetcharg[:type]\n"
 	"\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
 #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
+#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
+	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>, <argname>\n"
+#else
 	"\t           $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+#endif
 #else
 	"\t           $stack<index>, $stack, $retval, $comm,\n"
 #endif

kernel/trace/trace_fprobe.c

@@ -366,6 +366,7 @@ static void free_trace_fprobe(struct trace_fprobe *tf)
 static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 					       const char *event,
 					       const char *symbol,
+					       struct tracepoint *tpoint,
 					       int maxactive,
 					       int nargs, bool is_return)
 {
@@ -385,6 +386,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 	else
 		tf->fp.entry_handler = fentry_dispatcher;
 
+	tf->tpoint = tpoint;
 	tf->fp.nr_maxactive = maxactive;
 
 	ret = trace_probe_init(&tf->tp, event, group, false);
@@ -930,8 +932,12 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	int maxactive = 0;
 	char buf[MAX_EVENT_NAME_LEN];
 	char gbuf[MAX_EVENT_NAME_LEN];
-	unsigned int flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE;
+	char sbuf[KSYM_NAME_LEN];
 	bool is_tracepoint = false;
+	struct tracepoint *tpoint = NULL;
+	struct traceprobe_parse_context ctx = {
+		.flags = TPARG_FL_KERNEL | TPARG_FL_FPROBE,
+	};
 
 	if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2)
 		return -ECANCELED;
@@ -995,14 +1001,6 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		goto parse_error;
 	}
 
-	if (is_return)
-		flags |= TPARG_FL_RETURN;
-	else
-		flags |= TPARG_FL_FENTRY;
-
-	if (is_tracepoint)
-		flags |= TPARG_FL_TPOINT;
-
 	trace_probe_log_set_index(0);
 	if (event) {
 		ret = traceprobe_parse_event_name(&event, &group, gbuf,
@@ -1014,16 +1012,36 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 	if (!event) {
 		/* Make a new event name */
 		if (is_tracepoint)
-			strscpy(buf, symbol, MAX_EVENT_NAME_LEN);
+			snprintf(buf, MAX_EVENT_NAME_LEN, "%s%s",
+				 isdigit(*symbol) ? "_" : "", symbol);
 		else
 			snprintf(buf, MAX_EVENT_NAME_LEN, "%s__%s", symbol,
 				 is_return ? "exit" : "entry");
 		sanitize_event_name(buf);
 		event = buf;
 	}
 
+	if (is_return)
+		ctx.flags |= TPARG_FL_RETURN;
+	else
+		ctx.flags |= TPARG_FL_FENTRY;
+
+	if (is_tracepoint) {
+		ctx.flags |= TPARG_FL_TPOINT;
+		tpoint = find_tracepoint(symbol);
+		if (!tpoint) {
+			trace_probe_log_set_index(1);
+			trace_probe_log_err(0, NO_TRACEPOINT);
+			goto parse_error;
+		}
+		ctx.funcname = kallsyms_lookup(
+				(unsigned long)tpoint->probestub,
+				NULL, NULL, NULL, sbuf);
+	} else
+		ctx.funcname = symbol;
+
 	/* setup a probe */
-	tf = alloc_trace_fprobe(group, event, symbol, maxactive,
+	tf = alloc_trace_fprobe(group, event, symbol, tpoint, maxactive,
 				argc - 2, is_return);
 	if (IS_ERR(tf)) {
 		ret = PTR_ERR(tf);
@@ -1032,24 +1050,15 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 		goto out;	/* We know tf is not allocated */
 	}
 
-	if (is_tracepoint) {
-		tf->tpoint = find_tracepoint(tf->symbol);
-		if (!tf->tpoint) {
-			trace_probe_log_set_index(1);
-			trace_probe_log_err(0, NO_TRACEPOINT);
-			goto parse_error;
-		}
+	if (is_tracepoint)
 		tf->mod = __module_text_address(
 				(unsigned long)tf->tpoint->probestub);
-	}
 
 	argc -= 2; argv += 2;
-
 	/* parse arguments */
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
-		struct traceprobe_parse_context ctx = { .flags = flags };
-
 		trace_probe_log_set_index(i + 2);
+		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tf->tp, i, argv[i], &ctx);
 		if (ret)
 			goto error;	/* This can be -ENOMEM */

kernel/trace/trace_kprobe.c

@@ -742,7 +742,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
 	char gbuf[MAX_EVENT_NAME_LEN];
-	unsigned int flags = TPARG_FL_KERNEL;
+	struct traceprobe_parse_context ctx = { .flags = TPARG_FL_KERNEL };
 
 	switch (argv[0][0]) {
 	case 'r':
@@ -823,10 +823,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 			goto parse_error;
 		}
 		if (is_return)
-			flags |= TPARG_FL_RETURN;
+			ctx.flags |= TPARG_FL_RETURN;
 		ret = kprobe_on_func_entry(NULL, symbol, offset);
 		if (ret == 0 && !is_return)
-			flags |= TPARG_FL_FENTRY;
+			ctx.flags |= TPARG_FL_FENTRY;
 		/* Defer the ENOENT case until register kprobe */
 		if (ret == -EINVAL && is_return) {
 			trace_probe_log_err(0, BAD_RETPROBE);
@@ -856,7 +856,7 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 
 	/* setup a probe */
 	tk = alloc_trace_kprobe(group, event, addr, symbol, offset, maxactive,
-			       argc - 2, is_return);
+				argc - 2, is_return);
 	if (IS_ERR(tk)) {
 		ret = PTR_ERR(tk);
 		/* This must return -ENOMEM, else there is a bug */
@@ -866,10 +866,10 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 	argc -= 2; argv += 2;
 
 	/* parse arguments */
+	ctx.funcname = symbol;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
-		struct traceprobe_parse_context ctx = { .flags = flags };
-
 		trace_probe_log_set_index(i + 2);
+		ctx.offset = 0;
 		ret = traceprobe_parse_probe_arg(&tk->tp, i, argv[i], &ctx);
 		if (ret)
 			goto error;	/* This can be -ENOMEM */